OSNews:

OSNews: http://www.osnews.com/story/22571/Intel_Shows_Off_48-Core_Chip Exploring the Future of Computing en-us Copyright 2001-2013, David Adams adam+nospam@osnews.com Wed, 19 Jun 2013 00:13:26 GMT http://www.osnews.com/images/osnews.gif OSNews.com http://www.osnews.com Flash http://www.osnews.com/thread?397818 http://www.osnews.com/thread?397818 ...and flash video will still be slow as hell... Thu, 03 Dec 2009 23:33:00 GMT donotreply@osnews.com (Cody Evans) Comments 27 million transistors per core http://www.osnews.com/thread?397847 http://www.osnews.com/thread?397847 Note that each core is roughly comparable to a Pentium 3. And that the whole thing has about twice as many transistors as Nahalem.

It's flexible. But not all that powerful. Fri, 04 Dec 2009 01:25:00 GMT donotreply@osnews.com (sbergman27) Comments RE: Flash http://www.osnews.com/thread?397896 http://www.osnews.com/thread?397896 Only on Linux. Fri, 04 Dec 2009 07:10:00 GMT donotreply@osnews.com (flanque) Comments RE: 27 million transistors per core http://www.osnews.com/thread?397897 http://www.osnews.com/thread?397897 Its about parallel processing, rather than brute force. Fri, 04 Dec 2009 07:11:00 GMT donotreply@osnews.com (flanque) Comments RE: Flash http://www.osnews.com/thread?397898 http://www.osnews.com/thread?397898 Intel can't fix a problem created and prolonged by Adobe. Fri, 04 Dec 2009 07:11:00 GMT donotreply@osnews.com (cerbie) Comments RE: 27 million transistors per core http://www.osnews.com/thread?397907 http://www.osnews.com/thread?397907 I've read that it's based on P55C architecture, so that would make it more like a massively parallel Pentium MMX.

Isn't that P5 architeccture essentially what the Atom is based on? Fri, 04 Dec 2009 08:18:00 GMT donotreply@osnews.com (Cytor) Comments The problem is the software http://www.osnews.com/thread?397910 http://www.osnews.com/thread?397910 The major problem now is the software. Most software out their today do not take into account multi-core CPU's, so it's as if they run on a single core anyway (mostly single threaded applications).

Yes the OS can do some scheduling, but it's down to the software applications to take charge of multi-cores and multi-threading. Fri, 04 Dec 2009 08:49:00 GMT donotreply@osnews.com (ggeldenhuys) Comments RE: The problem is the software http://www.osnews.com/thread?397911 http://www.osnews.com/thread?397911 Erlang @ http://www.erlang.org/ just do that kind of stuff, massive multi-core programming, and with ease and elegance

Kochise Fri, 04 Dec 2009 09:16:00 GMT donotreply@osnews.com (Kochise) Comments RE[2]: 27 million transistors per core http://www.osnews.com/thread?397919 http://www.osnews.com/thread?397919 I've read that it's based on P55C architecture,
You couldn't read about this chip, because there is no public info except of this announcement.
It is not a Larrabee, but different CPU. Althought they could reuse the core.

Isn't that P5 architeccture essentially what the Atom is based on?
Atom has nothing to do with P5. It is totally different. Fri, 04 Dec 2009 11:08:00 GMT donotreply@osnews.com (viton) Comments RE[3]: 27 million transistors per core http://www.osnews.com/thread?397921 http://www.osnews.com/thread?397921 Well, German online magazine heise.de says, these are similar to P55C-cores. They do not name sources, tough.
Link Fri, 04 Dec 2009 11:18:00 GMT donotreply@osnews.com (Cytor) Comments RE[2]: Flash http://www.osnews.com/thread?397939 http://www.osnews.com/thread?397939

Intel can't fix a problem created and prolonged by Adobe.

He wasn't blaming Intel, read the damn post, it was prety obvious he was talking about the fact that no matter how much power is thrown at Flash, it still sucks. Fri, 04 Dec 2009 13:34:00 GMT donotreply@osnews.com (kaiwai) Comments RE: The problem is the software http://www.osnews.com/thread?397943 http://www.osnews.com/thread?397943

The major problem now is the software. Most software out their today do not take into account multi-core CPU's, so it's as if they run on a single core anyway (mostly single threaded applications).

Yes the OS can do some scheduling, but it's down to the software applications to take charge of multi-cores and multi-threading.

This wont be targeted at general consumers (who, for now, most new computers are sufficiently powerful).

This will be targeted at mainframe users who already do complicated distributed processing or server admins who want to consolidate several hardware resources into one host running several virtual machines (each assigned 2 or more cores)

For these users - this type of CPU is the future.Edited 2009-12-04 14:25 UTC Fri, 04 Dec 2009 14:25:00 GMT donotreply@osnews.com (Laurence) Comments I wonder what Intel could come up with... http://www.osnews.com/thread?397949 http://www.osnews.com/thread?397949 ...if they took a year off from their current chip designs and try to innovate a little, maybe come up with a chip that is super conductive, or perhaps optic or chemical in nature instead of using electricity as the driving force. Fri, 04 Dec 2009 15:08:00 GMT donotreply@osnews.com (Tuishimi) Comments RE: The problem is the software http://www.osnews.com/thread?397955 http://www.osnews.com/thread?397955

The major problem now is the software. Most software out their today do not take into account multi-core CPU's, so it's as if they run on a single core anyway (mostly single threaded applications).

Depends on what software you are talking about. I guess a 48 core cpu isn't intended for the flash playing/web browsing user, but for servers and hard core desktops (designers, CAD, gaming). Most desktop and single threaded applications won't ever need so many cores. Fri, 04 Dec 2009 15:33:00 GMT donotreply@osnews.com (sbenitezb) Comments RE[2]: The problem is the software http://www.osnews.com/thread?397958 http://www.osnews.com/thread?397958

Most desktop and single threaded applications won't ever need so many cores.

Except when they're loaded with malware - in which case the more cores there are to run the malware in the background, the better the user experience will be

Fri, 04 Dec 2009 15:44:00 GMT donotreply@osnews.com (umccullough) Comments RE[2]: The problem is the software http://www.osnews.com/thread?398044 http://www.osnews.com/thread?398044 I've just not been able to get used to the syntax yet. Sat, 05 Dec 2009 00:09:00 GMT donotreply@osnews.com (Lennie) Comments RE[3]: The problem is the software http://www.osnews.com/thread?398046 http://www.osnews.com/thread?398046 I have a feeling more malware does not make for a better user experience. Sat, 05 Dec 2009 00:14:00 GMT donotreply@osnews.com (Lennie) Comments RE[3]: Flash http://www.osnews.com/thread?398061 http://www.osnews.com/thread?398061 He said Flash video, which works fine for nVidia users, and Adobe could make it work fine for everyone using Flash, if they so desired.

If it were about throwing power at it, then it makes no sense, as these 48-core CPUs would be pitiful at that kind of work, even if Flash didn't suck. Sat, 05 Dec 2009 04:07:00 GMT donotreply@osnews.com (cerbie) Comments RE: The problem is the software http://www.osnews.com/thread?398107 http://www.osnews.com/thread?398107 Clojure

http://clojure.org Sat, 05 Dec 2009 14:45:00 GMT donotreply@osnews.com (wannabe geek) Comments One word: Stream http://www.osnews.com/thread?398136 http://www.osnews.com/thread?398136 As someone who's writing C code that compiles to CUDA, you'll excuse me if the idea of a mere 48 cores on one die isn't exactly blowing my skirt up... The 'crappy' little Ge8800GTS driving my secondary displays has more cores than that - My primary GTX260 has 216 stream cores, and that new ATI 5970 everyone's raging about has what, 1600 stream processor cores per die? Sure, they are "stream processor cores", but that's still basically a processor unto itself (albeit a very data-oriented one) as evidenced by how much can be done in them from CUDA.

I really see this as Intel's response to losing share in the high performance arena due to things like CUDA - much like ATI's "Stream" if that ever becomes anything more than stillborn. (since I don't know ANYONE actually writing code to support ATI Stream) - or more specifically nVidia's Tesla.

Hell, look at the C2050 Tesla, 512 thread processors on one die - GPGPU's are threatening Intel's relevance - increasingly I suspect that as more and more computing is offloaded VIA technologies like CUDA we are likely to see x86 or even normal RISC CPU's relegated to being little more than legacy support and glorified traffic cops and I/O handlers, with parallel processing GPGPU's handling the real grunt work.

We have historical precedence for this approach too - look at the move from 8 bit to 16 bit with the Z80 and 68K. Trash-80 model 16 used a Z80 to handle keyboard/floppy/ports as well as running older Model II software, while the included 68K handled the gruntwork of running actual userspace programs. The Lisa and original mac were similarly divided, though they didn't use their Z80 for legacy... Or even look a few years later in the game console world where the Sega Genesis was a 68K and a Z80, the Z80 used to handle the VDP, two sound chips, and provide legacy support back to the SMS/SG-1000, while new games used the 68k for it's userland.

As such Intel is late to the party on using lots of simpler processors on one die - time will tell if that's going to be too little, too late. If they work it out so you could mount it alongside x86 and give it a compatibility layer for CUDA code (which nVidia more than approves of other companies doing) they might make a showing.

If not, it's going to end up just as stillborn as ATI's "stream" Sat, 05 Dec 2009 22:16:00 GMT donotreply@osnews.com (deathshadow) Comments RE: The problem is the software http://www.osnews.com/thread?398202 http://www.osnews.com/thread?398202 ... and that is why this is a research vehicle. Jesus, do some of you bother to even read the article before becoming Capt. Obvious? Sun, 06 Dec 2009 23:29:00 GMT donotreply@osnews.com (tylerdurden) Comments RE[2]: The problem is the software http://www.osnews.com/thread?398203 http://www.osnews.com/thread?398203 I take intel branding this as a "research chip for cloud computing" was not enough of a hint that this was not intended to be a desktop chip? Sun, 06 Dec 2009 23:47:00 GMT donotreply@osnews.com (tylerdurden) Comments